Qwen 3.5 2B (Non-reasoning): benchmark results
Qwen 3.5 2B evaluated with reasoning disabled. Provider: Alibaba. Released 2026-03-02. Access: Open.
Unified ELO 1429 ± 1, rank #1219 of 1761 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 81.58 | Accuracy (%) | 72.3 |
| AA Omniscience - Software Engineering (SWE) - Julia | 12 | Accuracy (%) | 58 |
| UGI - Willingness (W/10) | 6 | W/10 Score | 54.2 |
| UGI - Writing | 29 | Writing Score | 33.3 |
| AA Humanity's Last Exam | 4.96 | Accuracy (%) | 29.7 |
| AA Omniscience - Software Engineering (SWE) - R | 4 | Accuracy (%) | 25.8 |
| AA Terminal-Bench Hard | 3.79 | Accuracy (%) | 25.6 |
| AA CritPt | 0 | Accuracy (%) | 24.4 |
| UGI Leaderboard | 25.94 | UGI Score | 21.3 |
| AA Omniscience - Software Engineering (SWE) - Go | 8 | Accuracy (%) | 20 |
| AA GPQA Diamond | 43.84 | Accuracy (%) | 19.2 |
| AA Long Context Reasoning | 14 | Accuracy (%) | 19.2 |
Interactive version: theaggregate.ai/model?slug=qwen-3-5-2b-non-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.